Search Results for author: Wolfgang Merkt

Found 12 papers, 2 papers with code

Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization

no code implementations26 Sep 2022 Luigi Campanaro, Siddhant Gangapurwala, Wolfgang Merkt, Ioannis Havoutis

As an alternative, we investigate a simple strategy of random force injection (RFI) to perturb system dynamics during training.

Domain Adaptation

Agile Maneuvers in Legged Robots: a Predictive Control Approach

no code implementations14 Mar 2022 Carlos Mastalli, Wolfgang Merkt, Guiyang Xin, Jaehyun Shim, Michael Mistry, Ioannis Havoutis, Sethu Vijayakumar

To the best of our knowledge, our predictive controller is the first to handle actuation limits, generate agile locomotion maneuvers, and execute optimal feedback policies for low level torque control without the use of a separate whole-body controller.

Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion

no code implementations9 Dec 2021 Alexander L. Mitchell, Wolfgang Merkt, Mathieu Geisert, Siddhant Gangapurwala, Martin Engelcke, Oiwi Parker Jones, Ioannis Havoutis, Ingmar Posner

This encourages disentanglement such that application of a drive signal to a single dimension of the latent state induces holistic plans synthesising a continuous variety of trot styles.

Disentanglement

CPG-ACTOR: Reinforcement Learning for Central Pattern Generators

no code implementations25 Feb 2021 Luigi Campanaro, Siddhant Gangapurwala, Daniele De Martini, Wolfgang Merkt, Ioannis Havoutis

Our results on a locomotion task using a single-leg hopper demonstrate that explicitly using the CPG as the Actor rather than as part of the environment results in a significant increase in the reward gained over time (6x more) compared with previous approaches.

Robotics

A Passive Navigation Planning Algorithm for Collision-free Control of Mobile Robots

no code implementations1 Nov 2020 Carlo Tiseo, Vladimir Ivan, Wolfgang Merkt, Ioannis Havoutis, Michael Mistry, Sethu Vijayakumar

In literature, there are multiple model- and learning-based approaches that require significant computational resources to be effectively deployed and they may have limited generality.

Robotics

Memory Clustering using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-starts

no code implementations2 Oct 2020 Wolfgang Merkt, Vladimir Ivan, Traiko Dinev, Ioannis Havoutis, Sethu Vijayakumar

We demonstrate our method on a cart-pole toy problem and a quadrotor avoiding obstacles, and show that clustering samples based on inherent structure improves the warm-start quality.

A Feasibility-Driven Approach to Control-Limited DDP

1 code implementation1 Oct 2020 Carlos Mastalli, Wolfgang Merkt, Josep Marti-Saumell, Henrique Ferrolho, Joan Sola, Nicolas Mansard, Sethu Vijayakumar

Differential dynamic programming (DDP) is a direct single shooting method for trajectory optimization.

Predicted Composite Signed-Distance Fields for Real-Time Motion Planning in Dynamic Environments

no code implementations3 Aug 2020 Mark Nicholas Finean, Wolfgang Merkt, Ioannis Havoutis

We present a novel framework for motion planning in dynamic environments that accounts for the predicted trajectories of moving objects in the scene.

Motion Planning Robotics Systems and Control Systems and Control

Learning Whole-body Motor Skills for Humanoids

no code implementations7 Feb 2020 Chuanyu Yang, Kai Yuan, Wolfgang Merkt, Taku Komura, Sethu Vijayakumar, Zhibin Li

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i. e., ankle, hip, foot tilting, and stepping strategies.

Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control

2 code implementations11 Sep 2019 Carlos Mastalli, Rohan Budhiraja, Wolfgang Merkt, Guilhem Saurel, Bilal Hammoud, Maximilien Naveau, Justin Carpentier, Ludovic Righetti, Sethu Vijayakumar, Nicolas Mansard

Additionally, we propose a novel optimal control algorithm called Feasibility-driven Differential Dynamic Programming (FDDP).

Robotics Optimization and Control

Cannot find the paper you are looking for? You can Submit a new open access paper.